Sakana AI

Sakana AI: Fugu Ultra

sakana/fugu-ultra

Access Fugu Ultra from Sakana AI using Puter.js AI API.

Get Started
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms", {
    model: "sakana/fugu-ultra"
}).then(response => {
    document.body.innerHTML = response.message.content;
});
<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "sakana/fugu-ultra"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.puter.com/puterai/openai/v1/",
    api_key="YOUR_PUTER_AUTH_TOKEN",
)

response = client.chat.completions.create(
    model="sakana/fugu-ultra",
    messages=[
        {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
)

print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
  -d '{
    "model": "sakana/fugu-ultra",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Fugu Ultra is a learned multi-agent orchestration system from Tokyo-based Sakana AI that routes tasks across a swappable pool of frontier LLMs behind a single OpenAI-compatible endpoint.

Rather than relying on one monolithic model, Fugu Ultra dynamically assigns Thinker, Worker, and Verifier roles to specialist agents, then synthesizes their outputs into a single response. The underlying coordination is grounded in Sakana's TRINITY and Conductor research, published at ICLR 2026.

It targets demanding, multi-step problems: complex reasoning, code review, agentic workflows, cybersecurity analysis, and research tasks. On LiveCodeBench it scores 93.2, ahead of several frontier competitors, and it matches leading models on GPQA-Diamond and Humanity's Last Exam.

Fugu Ultra is a strong choice for developers who need frontier-level quality on hard tasks without committing to a single model provider.

Context Window 1M

tokens

Max Output 128K

tokens

Input Cost $5

per million tokens

Output Cost $30

per million tokens

Release Date Jun 24, 2026

 

Model Playground

Try Fugu Ultra instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat sakana/fugu-ultra
Sakana AI
Chat with Fugu Ultra
Powered by Puter.js

Frequently Asked Questions

How do I use Fugu Ultra?

You can access Fugu Ultra by Sakana AI through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Is Fugu Ultra free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Fugu Ultra to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for Fugu Ultra?
Fugu Ultra costs $5 per 1M input tokens and $30 per 1M output tokens.
Price per 1M tokens
Input$5
Output$30
Who created Fugu Ultra?

Fugu Ultra was created by Sakana AI and released on Jun 24, 2026.

What is the context window of Fugu Ultra?

Fugu Ultra supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,000 pages of text.

What is the max output length of Fugu Ultra?

Fugu Ultra can generate up to 128K tokens in a single response.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Fugu Ultra API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add Fugu Ultra to your app without worrying about API keys or setup.

Read the Docs View Tutorials